The tool we developed, called Prompt Poets, allows us to template our prompts using YAML and Ginger, enabling us to manage runtime variables and control flow effectively.

We're currently working on a project called Henson, which aims to get deep learning models to generate new sounds, focusing on improving the quality and usability of the generated audio.

We're launching open-source evaluators that simplify the process of evaluating code, retrieval-augmented generation, extraction, and tool calling, making it easier for developers to get started.

Using large language models as prototyping tools can be effective; they allow for rapid development and testing of ideas before creating more specialized models tailored to specific tasks.

Humanloop enables large language models to have enhanced capabilities, allowing you to build differentiated applications and products on top of these models, with the range of use cases limited more by imagination than by technology.

Canvas leverages OpenAI's model to generate comprehensive code, allowing users who may not know how to code to quickly mock up prototypes.

In February, we launched the research preview of GPT-4.5, which is more intuitive and collaborative than previous models, making collaboration significantly easier.

Open source models like Tulu aim to provide accessible tools for fine-tuning AI models to specific domains, promoting innovation.

We built a tool to streamline the process of iterating on our prompting layer, allowing us to run experiments and assess the impact of even trivial changes on performance and user engagement.